Image Hosting solution, Flickr/imgur alternative, make it easy for users to share their images. Using Cloudflare Pages and Telegraph.

The easiest way to use Agentic RAG in any enterprise

PyGWalker: Turn your pandas dataframe into an interactive UI for visual analysis

Optimized implementation for color-icon-matrix barcodes

🥧 The Cross-Platform Pie Menu.

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

Brand new TTS solution

Python library for converting Python calculations into rendered latex.

🧑‍🚀 全世界最好的LLM资料总结 | Summary of the world's best LLM resources.

Awesome LLMs on Device: A Comprehensive Survey

🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.

A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…

Lightweight library for scraping web-sites with LLMs

A rule-based tunnel in Go.

Another Mihomo GUI.

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Free ChatGPT API Key，免费ChatGPT API，支持GPT4 API（免费），ChatGPT国内可用免费转发API，直连无需代理。可以搭配ChatBox等软件/插件使用，极大降低接口使用成本。国内即可无限制畅快聊天。

Linux命令大全搜索工具，内容包含Linux命令手册、详解、学习、搜集。https://git.io/linux

real time face swap and one-click video deepfake with only a single image

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

🚀 DeepSeek-V2大模型逆向API白嫖测试【特长：GPT4平替】，支持高速流式输出、多轮对话，零配置部署，多路token支持。

Wiseflow is an agile information mining tool that extracts concise messages from various sources such as websites, WeChat official accounts, social platforms, etc. It automatically categorizes and …

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Learning English through the method of constructing sentences with conjunctions

🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

Finetune Llama 3.2, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

A Node.js CLI that uses Ollama and LM Studio models (Llava, Gemma, Llama etc.) to intelligently rename files by their contents

Official electron build of draw.io

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)